Load data
library(here)
source(here("00-load-libraries.R"))
load(here("data","attribs.Rdata")) # from 01-prep-attribute-tables.Rmd
load(here("data","attributes_merged_clean.Rdata"))
Hierarchical Clustering Analyses
# Plot Dendrogram for Case Studies
# Prepare data for performing clustering analysis
case_clustering <- attributes_merged_clean %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = official_score, values_fill = 0)
# Prepare data for dendrogram
# Scale the data
case_scaled <- case_clustering
case_scaled[, c(2:39)] <- scale(case_scaled[, 2:39])
# Run clustering
case_matrix <- as.matrix(case_scaled[, -c(1)])
rownames(case_matrix) <- case_scaled$case_study
case_dendro <- as.dendrogram(hclust(d = dist(x = case_matrix)))
# Plot the dendrogram
case_dendrogram_plot <- ggdendrogram(data = case_dendro, rotate = TRUE) +
labs(title = "Hierarchical Clustering of Case Studies")
print(case_dendrogram_plot)
# Plot Dendrogram for Attributes
# Prepare data for performing clustering analysis
attributes_clustering <- attributes_merged_clean %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = case_study, values_from = official_score, values_fill = 0)
# Prepare data for dendrogram
# Scale the data
attributes_scaled <- attributes_clustering
attributes_scaled[, c(2:13)] <- scale(attributes_scaled[, 2:13])
# Run clustering
attributes_matrix <- as.matrix(attributes_scaled[, -c(1)])
rownames(attributes_matrix) <- attributes_scaled$attribute
attributes_dendro <- as.dendrogram(hclust(d = dist(x = attributes_matrix)))
# Plot the dendrogram
attributes_dendrogram_plot <- ggdendrogram(data = attributes_dendro, rotate = TRUE) +
labs(title = "Hierarchical Clustering of Attributes")
print(attributes_dendrogram_plot)
Hierarchical Clustering Analyses (by Dimension)
# Ecologcial Hiearchical Clustering
# Prepare data for performing clustering analysis
ecological_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Ecological") %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = case_study, values_from = official_score, values_fill = 0)
# Prepare data for dendrogram
# Scale the data
ecological_scaled <- ecological_clustering
ecological_scaled[, c(3:15)] <- scale(ecological_scaled[, 3:15])
# Run clustering
ecological_matrix <- as.matrix(ecological_scaled[, -c(1:2)])
rownames(ecological_matrix) <- ecological_scaled$attribute
ecological_dendro <- as.dendrogram(hclust(d = dist(x = ecological_matrix)))
# Plot the dendrogram
ecological_dendrogram_plot <- ggdendrogram(data = ecological_dendro, rotate = TRUE) +
labs(title = "Hierarchical Clustering of Attributes for Ecological Dimension")
print(ecological_dendrogram_plot)
## Socio-Economic Hiearchical Clustering
# Prepare data for performing clustering analysis
socio_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Social-economic") %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = case_study, values_from = official_score, values_fill = 0)
# Prepare data for dendrogram
# Scale the data
socio_scaled <- socio_clustering
socio_scaled[, c(3:14)] <- scale(socio_scaled[, 3:14])
# Run clustering
socio_matrix <- as.matrix(socio_scaled[, -c(1:2)])
rownames(socio_matrix) <- socio_scaled$attribute
socio_dendro <- as.dendrogram(hclust(d = dist(x = socio_matrix)))
# Plot the dendrogram
socio_dendrogram_plot <- ggdendrogram(data = socio_dendro, rotate = TRUE) +
labs(title = "Hierarchical Clustering of Attributes for Socio-Economic Dimension")
print(socio_dendrogram_plot)
## Governance Hiearchical Clustering
# Prepare data for performing clustering analysis
governance_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Goverance") %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = case_study, values_from = official_score, values_fill = 0)
# Prepare data for dendrogram
# Scale the data
governance_scaled <- governance_clustering
governance_scaled[, c(3:14)] <- scale(governance_scaled[, 3:14])
# Run clustering
governance_matrix <- as.matrix(governance_scaled[, -c(1:2)])
rownames(governance_matrix) <- governance_scaled$attribute
governance_dendro <- as.dendrogram(hclust(d = dist(x = governance_matrix)))
# Plot the dendrogram
governance_dendrogram_plot <- ggdendrogram(data = governance_dendro, rotate = TRUE) +
labs(title = "Hierarchical Clustering of Attributes for Governance Dimension")
print(governance_dendrogram_plot)
Heatmap Analyses
# Create theme
my_theme <- theme(axis.text.x=element_text(size=8, angle=35, hjust=1),
axis.text.y=element_text(size=8),
axis.title=element_text(size=9),
legend.text=element_text(size=8),
legend.title=element_text(size=9),
strip.text=element_text(size=9),
plot.title=element_text(size=10),
# Gridlines
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_rect(),
axis.line = element_line())
# Data wrangling to organize importance clustering
score_clustering <- attributes_merged_clean %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = official_score, values_fill = 0)
# Heatmap of Importance Scores Across all Attributes
# Select the appropriate columns
score_long <- melt(score_clustering, id = c("case_study"))
# Create heatmap
score_heatmap_plot <- ggplot(data = score_long,
aes(x = case_study, y = variable, text=value)) +
geom_tile(aes(fill = value)) +
labs(title = "Heatmap of Attribute Scores Across all Attributes", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme +
geom_hline(yintercept = "Population modularity",
color = "black",
linetype = "solid") +
geom_hline(yintercept = "Agency",
color = "black",
linetype = "solid")
score_heatmap_plot
# Make the graph interactive
#ggplotly(importance_heatmap_plot, tooltip="text")
# Data wrangling to organize importance clustering
importance_clustering <- attributes_merged_clean %>%
select(case_study, attribute, numeric_importance) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = numeric_importance, values_fill = 0)
# Heatmap of Importance Scores Across all Attributes
# Select the appropriate columns
importance_long <- melt(importance_clustering, id = c("case_study"))
# Create heatmap
importance_heatmap_plot <- ggplot(data = importance_long,
aes(x = case_study, y = variable, text=value)) +
geom_tile(aes(fill = value)) +
labs(title = "Heatmap of Importance Scores Across all Attributes", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme +
geom_hline(yintercept = "Population modularity",
color = "black",
linetype = "solid") +
geom_hline(yintercept = "Agency",
color = "black",
linetype = "solid")
importance_heatmap_plot
# Make the graph interactive
#ggplotly(importance_heatmap_plot, tooltip="text")
Heatmap Comparison
# Eliminate legends to make patchwork cleaner
p1 <- score_heatmap_plot +
theme(legend.position = "none")
p2 <- importance_heatmap_plot+
theme(legend.position = "none")
# Use patchwork to plot the heatmaps next to each other
p1 | p2
Interactive Heatmaps for Attribute Scores (by Dimension)
# Ecological Heatmap
# Prepare data for performing clustering analysis
eco_heat_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Ecological") %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = official_score, values_fill = 0)
# Select the appropriate columns
eco_long <- melt(eco_heat_clustering, id = c("case_study"))
# Create heatmap
eco_heatmap_plot <- ggplot(data = eco_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Ecological Attribute Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme
# Preview the heatmap
ggplotly(eco_heatmap_plot, tooltip="text")
# Socio-Economic Heatmap
# Prepare data for performing clustering analysis
socio_heat_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Social-economic") %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = official_score, values_fill = 0)
# Select the appropriate columns
socio_long <- melt(socio_heat_clustering, id = c("case_study"))
# Create heatmap
socio_heatmap_plot <- ggplot(data = socio_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Socio-Economic Attribute Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme
# Preview the heatmap
ggplotly(socio_heatmap_plot, tooltip="text")
# Governance Heatmap
# Prepare data for performing clustering analysis
gov_heat_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, official_score) %>%
filter(dimension == "Goverance") %>%
select(case_study, attribute, official_score) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = official_score, values_fill = 0)
# Select the appropriate columns
gov_long <- melt(gov_heat_clustering, id = c("case_study"))
# Create heatmap
gov_heatmap_plot <- ggplot(data = gov_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Governance Attribute Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() +my_theme
# Preview the heatmap
ggplotly(gov_heatmap_plot, tooltip="text")
Interactive Heatmaps for Importance Scores (by Dimension)
# Ecological Importance Heatmap
# Prepare data for performing clustering analysis
eco_importance_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, numeric_importance) %>%
filter(dimension == "Ecological") %>%
select(case_study, attribute, numeric_importance) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = numeric_importance, values_fill = 0)
# Select the appropriate columns
eco_importance_long <- melt(eco_importance_clustering, id = c("case_study"))
# Create heatmap
eco_importance_plot <- ggplot(data = eco_importance_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Ecological Importance Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme
# Preview the heatmap
ggplotly(eco_importance_plot, tooltip="text")
# Socio-economic Importance Heatmap
# Prepare data for performing clustering analysis
socio_importance_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, numeric_importance) %>%
filter(dimension == "Social-economic") %>%
select(case_study, attribute, numeric_importance) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = numeric_importance, values_fill = 0)
# Select the appropriate columns
socio_importance_long <- melt(socio_importance_clustering, id = c("case_study"))
# Create heatmap
socio_importance_plot <- ggplot(data = socio_importance_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Socio-Economic Importance Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme
# Preview the heatmap
ggplotly(socio_importance_plot, tooltip="text")
# Governance Importance Heatmap
# Prepare data for performing clustering analysis
gov_importance_clustering <- attributes_merged_clean %>%
select(case_study, dimension, attribute, numeric_importance) %>%
filter(dimension == "Goverance") %>%
select(case_study, attribute, numeric_importance) %>%
# Use `pivot_wider` function to decrease the number of rows and increase the number of columns
# Also do values_fill = 0 to convert NA values to 0
pivot_wider(names_from = attribute, values_from = numeric_importance, values_fill = 0)
# Select the appropriate columns
gov_importance_long <- melt(gov_importance_clustering, id = c("case_study"))
# Create heatmap
gov_importance_plot <- ggplot(data = gov_importance_long,
aes(x = case_study, y = variable, text = value)) +
geom_tile(aes(fill = value)) +
labs(title = "Goverance Importance Score Heatmap", x = "Case Studies", y = "Attributes") +
scale_fill_distiller(palette = "RdYlBu") +
theme(axis.text.y = element_text(size = 6)) +
theme_bw() + my_theme
# Preview the heatmap
ggplotly(gov_importance_plot, tooltip="text")
